3 days ago
Munich, GermanySenior
Responsibilities
- Integrate AI products handling real-time data from external sources and multiple systems.
- Route streaming responses and LLM requests across providers using fallback and cost-aware logic.
- Monitor latency, costs, and error rates and proactively address performance and reliability issues.
- Make architectural decisions that improve system quality while maintaining simple, maintainable designs.
- Build and improve observability, deployment safety, and incident practices.
- Contribute application code alongside DevOps or SRE work and frontend code when needed.
Requirements
- At least 3 years of backend engineering experience, including 3 or more years building production systems with TypeScript.
- Production experience with Docker and Kubernetes.
- Strong system design skills and sound reasoning about performance, latency, and cost.
- Working knowledge of PostgreSQL, APIs, queues, and caching.
- Experience improving platform reliability and performance under production load, including instrumentation, observability, and root-cause analysis.
- Familiarity with streaming responses or LLM request routing across providers, including fallback and cost considerations.
- Knowledge of zero-downtime migrations, rollback-capable deployments, secure defaults, permissions, and structured incident reviews is valuable.
Benefits
- Base salary of €60,000 to €90,000 annually.
- Hybrid work arrangement in Munich, Germany.
- Visa sponsorship is not available.